[PATCH 03/32] drm/i915: Postpone fake breadcrumb interrupt until real interrupts cease

[Chris Wilson]

When the timer expires for checking on interrupt processing, check to
see if any interrupts arrived within the last time period. If real
interrupts are still being delivered, we can be reassured that we
haven't missed the final interrupt as the waiter will still be woken.
Only once all activity ceases, do we have to worry about the waiter
never being woken and so need to install a timer to kick the waiter for
a slow arrival of a seqno.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c          |  1 +
 drivers/gpu/drm/i915/intel_breadcrumbs.c | 23 ++++++++++-------------
 drivers/gpu/drm/i915/intel_ringbuffer.h  |  3 ++-
 3 files changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 91be31617e78..57fa1bf78a85 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1033,6 +1033,7 @@ static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv)
 
 static void notify_ring(struct intel_engine_cs *engine)
 {
+	atomic_inc(&engine->irq_count);
 	set_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
 	if (intel_engine_wakeup(engine))
 		trace_i915_gem_request_notify(engine);
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 74cb7b91b5db..d229a555db25 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -26,6 +26,11 @@
 
 #include "i915_drv.h"
 
+static unsigned long wait_timeout(void)
+{
+	return round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES);
+}
+
 static void intel_breadcrumbs_hangcheck(unsigned long data)
 {
 	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
@@ -34,8 +39,9 @@ static void intel_breadcrumbs_hangcheck(unsigned long data)
 	if (!b->irq_enabled)
 		return;
 
-	if (time_before(jiffies, b->timeout)) {
-		mod_timer(&b->hangcheck, b->timeout);
+	if (b->hangcheck_interrupts != atomic_read(&engine->irq_count)) {
+		b->hangcheck_interrupts = atomic_read(&engine->irq_count);
+		mod_timer(&b->hangcheck, wait_timeout());
 		return;
 	}
 
@@ -55,11 +61,6 @@ static void intel_breadcrumbs_hangcheck(unsigned long data)
 	i915_queue_hangcheck(engine->i915);
 }
 
-static unsigned long wait_timeout(void)
-{
-	return round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES);
-}
-
 static void intel_breadcrumbs_fake_irq(unsigned long data)
 {
 	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
@@ -129,6 +130,7 @@ static void __intel_breadcrumbs_enable_irq(struct intel_breadcrumbs *b)
 
 	/* No interrupts? Kick the waiter every jiffie! */
 	if (intel_irqs_enabled(i915)) {
+		b->hangcheck_interrupts = 0;
 		if (!test_bit(engine->id, &i915->gpu_error.test_irq_rings))
 			irq_enable(engine);
 		b->irq_enabled = true;
@@ -140,8 +142,7 @@ static void __intel_breadcrumbs_enable_irq(struct intel_breadcrumbs *b)
 		i915_queue_hangcheck(i915);
 	} else {
 		/* Ensure we never sleep indefinitely */
-		GEM_BUG_ON(!time_after(b->timeout, jiffies));
-		mod_timer(&b->hangcheck, b->timeout);
+		mod_timer(&b->hangcheck, wait_timeout());
 	}
 }
 
@@ -258,7 +259,6 @@ static bool __intel_engine_add_wait(struct intel_engine_cs *engine,
 		GEM_BUG_ON(!next && !first);
 		if (next && next != &wait->node) {
 			GEM_BUG_ON(first);
-			b->timeout = wait_timeout();
 			b->first_wait = to_wait(next);
 			rcu_assign_pointer(b->irq_seqno_bh, b->first_wait->tsk);
 			/* As there is a delay between reading the current
@@ -286,7 +286,6 @@ static bool __intel_engine_add_wait(struct intel_engine_cs *engine,
 
 	if (first) {
 		GEM_BUG_ON(rb_first(&b->waiters) != &wait->node);
-		b->timeout = wait_timeout();
 		b->first_wait = wait;
 		rcu_assign_pointer(b->irq_seqno_bh, wait->tsk);
 		/* After assigning ourselves as the new bottom-half, we must
@@ -396,7 +395,6 @@ void intel_engine_remove_wait(struct intel_engine_cs *engine,
 			 * the interrupt, or if we have to handle an
 			 * exception rather than a seqno completion.
 			 */
-			b->timeout = wait_timeout();
 			b->first_wait = to_wait(next);
 			rcu_assign_pointer(b->irq_seqno_bh, b->first_wait->tsk);
 			if (b->first_wait->seqno != wait->seqno)
@@ -627,7 +625,6 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 
 	__intel_breadcrumbs_disable_irq(b);
 	if (intel_engine_has_waiter(engine)) {
-		b->timeout = wait_timeout();
 		__intel_breadcrumbs_enable_irq(b);
 		if (test_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted))
 			wake_up_process(b->first_wait->tsk);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 4ca5308e12bb..4091c97be6ec 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -213,6 +213,7 @@ struct intel_engine_cs {
 
 	struct intel_render_state *render_state;
 
+	atomic_t irq_count;
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
 #define ENGINE_IRQ_EXECLIST 1
@@ -245,7 +246,7 @@ struct intel_engine_cs {
 		struct timer_list fake_irq; /* used after a missed interrupt */
 		struct timer_list hangcheck; /* detect missed interrupts */
 
-		unsigned long timeout;
+		unsigned int hangcheck_interrupts;
 
 		bool irq_enabled : 1;
 		bool rpm_wakelock : 1;
-- 
2.11.0